Paper accepted at NAACL 2025
Abhinav Rao, Akhila Yerukola, Vishwa Shah, Katharina Reinecke, Maarten Sap
Paper accepted at NAACL 2024
Authors: Ramit Sawhney*, Shrey Pandit*, Vishwa Shah*, Megh Thakkar*, Shafiq Joty
(* - Equal contribution by authors)
Paper accepted at Interspeech 2022
Authors: Ramit Sawhney*, Megh Thakkar∗, Vishwa Shah∗, Puneet Mathur, Vasu Sharma, Dinesh Manocha
(* - Equal contribution by authors)
Knowledge-based Analogical Reasoning in Neuro-symbolic Latent Spaces
Paper accepted at 15th international workshop on neuro-symbolic learning and reasoning, IJCLR
Authors: Vishwa Shah, Aditya Sharma, Gautam Shroff, Lovekesh Vig, Tirtharaj Dash, Ashwin Srinivasan
Extended Abstract - Presented at 1st Workshop on Multilingual Representation Learning, EMNLP 2021
Authors: Megh Thakkar, Vishwa Shah, Ramit Sawhney and Debdoot Mukherjee
We presented an approach based on interpolative data augmentation method, Mixup, to improve the generalizability of models for POS tagging in cross-lingual settings. Through experiments on 10 languages with diverse structures and language roots, we put forward its applicability for downstream zero-shot cross-lingual tasks.
Presented at 4th Workshop on Data Engineering and Analytics, ICAI 2021
Authors: Dhvanil Sanghvi, Priya Deshpande, Suhas Shanbhogue, Vishwa Shah (Equal contribution by all authors)
Some more works under review!